Application of single-cell sequencing technology to the study of embryonic developmental toxicity of emerging contaminants: Progress and perspectives by Weizhao CAO, Yunhui ZHANG

“…However, challenges remain, including dataset bias, batch effects, and developmental differences between humans and model organisms. …”
Get full text

Spatio-Temporal AI Modeling for Urban Traffic Calibration: A SUMO-Based Approach by Pablo Manglano-Redondo, Alvaro Paricio-Garcia, Miguel A. Lopez-Carmona

“…At the core of the AI engine is the Dynamic Spatio-Temporal Graph Attention Network (DSTGAT), a hybrid model that combines multi-head Graph Attention Networks (GATv2) with Long Short-Term Memory (LSTM) networks. …”
Get full text

Deep learning-enhanced signal detection for communication systems. by Yang Liu, Peng Liu, Yu Shi, Xue Hao

“…At the same time, a DCNet decoder based on a convolutional neural network batch normalization mechanism is designed to suppress inter-subcarrier interference in OFDM systems effectively. …”
Get full text

PharmaLLM: A Medicine Prescriber Chatbot Exploiting Open-Source Large Language Models by Ayesha Azam, Zubaira Naz, Muhammad Usman Ghani Khan

“…PharmaLLM incorporates a multi-modal input/output mechanism, supporting both text and speech, to enhance accessibility. …”
Get full text

Resource Time Series Analysis and Forecasting in Large-Scale Virtual Clusters by Yue Lin, Jiamin Wen, Xudong Zhang, Yan Liang, Jianjiang Li

“…The model undergoes extensive offline training using a large volume of time series data, followed by deployment using TensorFlow Serving. Recent small-batch data are employed for fine-tuning model parameters to better adapt to current data patterns. …”
Get full text

High‐Performance Flexible Silicon Nanowire Field Effect Transistors on Plastic Substrates by Ting Zhang, Ying Sun, Ruijin Hu, Wentao Qian, Linwei Yu

“…The self‐aligned crystalline SiNW multi‐channels are first grown through an in‐plane solid–liquid–solid mechanism on rigid substrates, and then efficiently transferred in‐batch onto flexible polyethylene terephthalate (PET) plastics. …”
Get full text

Prediction of maximum forming depth in single point incremental forming of 6061 aluminum alloy based on Adaboost regression by LIANG Zhikai, ZHANG Zhichao, HU Lan, PANG Qiu

“…Single point incremental forming （SPIF） is a highly flexible manufacturing process widely utilized in the aerospace industry， particularly suited for customized and small-batch production components. However， the appropriate range of process parameters suitable for different models remains undefined， necessitating extensive parameter testing. …”
Get full text

Enhancing Methane Production Through Co‐Digestion of Sewage Sludge, Citrus Waste and Brewery Spend Grain With Natural Zeolite: Mechanisms and Microbiome Analysis by Aleksandra Szaja, Agnieszka Montusiewicz, Agnieszka Cydzik‐Kwiatkowska, Sylwia Pasieczna‐Patkowska, Magdalena Lebiocka

“…The experiments were conducted under mesophilic conditions at 37°C in batch mode; 7 series with differing feedstock configurations were performed. …”
Get full text

Attention mechanism based CNN-LSTM hybrid deep learning model for atmospheric ozone concentration prediction by Jiang Yuan, Hua Dengxin, Wang Yufeng, Yang Xueting, Di Huige, Yan Qing

“…It features an attention-based CNN-LSTM hybrid deep learning model with specific settings: a time step of 5, a batch size of 25, 15 units in the LSTM layer, the ReLU activation function, 25 epochs, and an overfitting avoidance strategy with a dropout rate of 0.15. …”
Get full text

CombiANT reader: Deep learning-based automatic image processing tool to robustly quantify antibiotic interactions. by Erik Hallström, Nikos Fatsis-Kavalopoulos, Manos Bimpis, Carolina Wählby, Anders Hast, Dan I Andersson

“…It could also aid large-scale antibiotic research by quickly processing hundreds of experiments in batch, obtaining better data, and ultimately supporting the development of better treatment strategies. …”
Get full text

A WGAN-GP Approach for Data Imputation in Photovoltaic Power Prediction by Zhu Liu, Lingfeng Xuan, Dehuang Gong, Xinlin Xie, Zhongwen Liang, Dongguo Zhou

“…To stabilize training, we introduce a gradient penalty mechanism and a single-batch multi-iteration strategy. Our contributions include analyzing the necessity of data imputation, designing a novel conditional GAN-based network for PV data generation, and validating the generated data using frequency domain analysis, t-NSE, and prediction performance. …”
Get full text

Data-driven cultural background fusion for environmental art image classification: Technical support of the dual Kernel squeeze and excitation network. by Chenchen Liu, Haoyue Guo

“…On this basis, the Rectified Linear Unit activation function and depthwise convolution are introduced after the second layer convolution, and batch normalization is performed to improve the efficiency and robustness of feature extraction. …”
Get full text

Accurately Identifying Different Ripening Stages of Strawberry Fruits in Complex Agricultural Scenarios by Xuefeng Ren, Yang Gan, Huan Liu, Yongming Chen, Ping Lin

“…Third, in the neck network, a multi-scale attention mechanism is introduced to preserve channel information and reduce computational overhead by reshaping selected channels into the batch dimension and grouping them into multiple sub-features, thereby facilitating the model’s perception of evenly distributed semantic features. …”
Get full text

Study of linear and nonlinear isotherm and kinetic parameters of hexavalent chromium adsorption onto reduced graphene oxide coated iron oxide by Selim Gürsoy, Nagehan Kübra Zeytinci, Buse Tuğba Zaman, Sezgin Bakırdere, Elif Öztürk Er

“…The nanocomposites were characterized using techniques including Fourier Transform Infrared Spectroscopy, X-Ray Diffraction Analysis, Scanning Electron Microscopy, Brunauer–Emmett–Teller surface area analysis, and Raman spectroscopy. The batch adsorption process was optimized by conducting response surface methods for assessing primary variables affecting the adsorption process. …”
Get full text

Reduction of tar, sulfur, chlorine and CO2 in syngas produced by gasification of refuse-derived fuel pellets by Matej Koritár, Juma Haydary

“…Gasification experiments were conducted in a two-stage batch reactor, and the produced syngas was purified using two continuous packed absorption columns. …”
Get full text

A Study on an Improved Generative Adversarial Network Model for Super-Resolution Image Reconstruction by Ximin Qu, Cheng Peng

“…To address these limitations, we propose an improved SRGAN model (denoted as SRGAN-GBDB) through multi-strategy collaborative optimization to improve reconstruction quality. …”
Get full text

Production, Validation, and Exposure Dose Measurement of [¹³N]Ammonia Under Academic Good Manufacturing Practice Environments by Katsumi Tomiyoshi, Yuta Namiki, David J. Yang, Tomio Inoue

“…These findings support the international harmonization of small-scale PET drug manufacturing in hospitals and clinics for future multi-center clinical trials and the development of a standard of care.…”
Get full text

Identification of NAPL Contamination Occurrence States in Low-Permeability Sites Using UNet Segmentation and Electrical Resistivity Tomography by Mengwen Gao, Yu Xiao, Xiaolei Zhang

“…A semantic segmentation model with skip connections and multi-scale feature fusion was developed based on the UNet architecture to achieve automatic identification of contaminated areas. …”
Get full text

A Self-Supervised Method for Speaker Recognition in Real Sound Fields with Low SNR and Strong Reverberation by Xuan Zhang, Jun Tang, Huiliang Cao, Chenguang Wang, Chong Shen, Jun Liu

“…The pre-trained model employs the Canopy/Mini Batch k-means++ strategy. In the TDNN architecture, several enhancements are implemented, including a cross-channel fusion mechanism based on Res2Net. …”
Get full text

Real-time surrogate compensation architecture for machine-tool thermal error compensation with high-performance model by Yubin Huang, Hongyou Hong, Huichen Zhou, Hua Xiang, Jianzhong Yang

“…Compared with the traditional Multi Liner Regression (MLR) model compensation method, the machining accuracy under complex working conditions is further improved by 50%.…”
Get full text